Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sleep-wake analysis method based on deep learning

A sleep-wake, deep learning technology, applied in the field of deep learning, can solve problems such as lack of computers, and achieve the effect of improving training speed, reducing model parameters, and improving accuracy.

Active Publication Date: 2022-07-05
ZHENGZHOU UNIV +1
View PDF19 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, some domestic algorithms have been applied in the field of sleep staging, but there is no relevant computer-aided sleep-wake analysis method in China

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sleep-wake analysis method based on deep learning
  • Sleep-wake analysis method based on deep learning
  • Sleep-wake analysis method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] Embodiment 1, a sleep-wake analysis method based on deep learning includes the following steps: Step 1: Collect multi-modal physiological signals during the whole sleep process of the subject through polysomnography, and select the breathing signals and breathing airflow of the abdomen and chest. and electro-oculogram, at the same time select the EEG of the 1st and 2nd leads for filtering and send the multimodal data to the model training, the collected signal is converted into a signal frequency of 200Hz, and the 30-second sliding window is 50% The overlap rate performs sample segmentation on the data, then averages and standard deviations of all samples in each dimension, and preprocesses the data through Z-Score standardization;

[0021] Step 2, the EEG signal of each sample preprocessed in step 1 Perform Fourier transform to convert into frequency domain features, and select the signal in the 0.5Hz-30Hz band to restore it to time series features through inverse Fou...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a sleep-wake analysis method based on deep learning, which includes the following steps: Step 1: collect multi-modal physiological signals during the whole sleep process of a subject through polysomnography, and select the breathing signals and breathing airflow of the abdomen and chest. and electrooculogram, at the same time select the EEG of the 1st and 2nd leads for filtering and send the multimodal data to the model training, the collected signal is converted into a signal frequency of 200Hz, and the 30-second sliding window is 50% The overlap rate samples the data, then averages and standard deviations of all samples in each dimension, and preprocesses the data through Z‑Score normalization, replacing the long short-term memory model by referencing the multi-head attention mechanism, and targeting at For sleep signal features, a large convolution kernel is designed for feature extraction. Experiments show that it greatly improves the model training speed, reduces model parameters, and effectively improves model analysis accuracy.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a sleep-wake analysis method based on deep learning. Background technique [0002] As an emerging borderline interdisciplinary subject, sleep medicine is receiving widespread attention. Its research helps to understand the important physiological mechanisms of the body, diagnose and treat sleep disorders, and improve sleep quality. Sleep is a complex physiological process and an important link in the recovery and consolidation of the body. With the increasing pressure of modern life, more and more people's sleep is affected, and there are even sleep disorders. Many cardiovascular diseases and mental diseases are also closely related to sleep. Lack of sleep can lead to a variety of adverse outcomes, including memory and learning impairments, obesity, irritability, cardiovascular dysfunction, hypotension, decreased immune function, and depression. Therefore, improvi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/00A61B5/372A61B5/398A61B5/08A61B5/087
CPCA61B5/4806A61B5/7267A61B5/08A61B5/087A61B5/369A61B5/398
Inventor 李润知周广鑫赵红领王菁张硕
Owner ZHENGZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com